vllm-project

vllm-project/vllm

steady

A high-throughput and memory-efficient inference and serving engine for LLMs

Python View on GitHub

Stars

92,358

Forks

22,486

Open issues

2,462

24h

+75

+0.1%

7d

+559

+0.6%

Refresh

1h

Star history (7 days)

Last checked

25m ago

Last pushed

1h ago

Next check

just now